ggplot2 the easiest path to graphics
qplot
data.table(facebook)
## userid age dob_day dob_year dob_month gender tenure friend_count
## 1: 2094382 14 19 1999 11 male 266 0
## 2: 1192601 14 2 1999 11 female 6 0
## 3: 2083884 14 16 1999 11 male 13 0
## 4: 1203168 14 25 1999 12 female 93 0
## 5: 1733186 14 4 1999 12 male 82 0
## ---
## 98999: 1268299 68 4 1945 4 female 541 2118
## 99000: 1256153 18 12 1995 3 female 21 1968
## 99001: 1195943 15 10 1998 5 female 111 2002
## 99002: 1468023 23 11 1990 4 female 416 2560
## 99003: 1397896 39 15 1974 5 female 397 2049
## friendships_initiated likes likes_received mobile_likes
## 1: 0 0 0 0
## 2: 0 0 0 0
## 3: 0 0 0 0
## 4: 0 0 0 0
## 5: 0 0 0 0
## ---
## 98999: 341 3996 18089 3505
## 99000: 1720 4401 13412 4399
## 99001: 1524 11959 12554 11959
## 99002: 185 4506 6516 4506
## 99003: 768 9410 12443 9410
## mobile_likes_received www_likes www_likes_received
## 1: 0 0 0
## 2: 0 0 0
## 3: 0 0 0
## 4: 0 0 0
## 5: 0 0 0
## ---
## 98999: 11887 491 6202
## 99000: 10592 2 2820
## 99001: 11462 0 1092
## 99002: 5760 0 756
## 99003: 9530 0 2913
qplot(dob_day,data=facebook)
qplot(dob_day,data=facebook,breaks = 1:31)
qplot(as.factor(dob_day),data=facebook)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
qplot(x=gender,y=friend_count,data=facebook)
qplot(x=gender,y=friend_count,data=facebook,geom="boxplot")
qplot(x=gender,y=friend_count,data=facebook,geom="boxplot",ylim = c(0, 1000))
qplot( friend_count,likes,data=facebook)
qplot( friend_count,likes,data=facebook,alpha=I(0.1) )
qplot( friend_count,likes,data=facebook,alpha=I(0.1), color=gender)
Themes
library(ggthemes)
base <- qplot(dob_day,data=facebook,breaks = 1:31)
base+theme_economist()+scale_colour_economist()
base+theme_tufte()
base<-base+theme_minimal()
base$labels
theme_set(theme_grey())
geom_histogram
base <- ggplot(aes(x = dob_day), data = facebook)
base
head(base$data)
## userid age dob_day dob_year dob_month gender tenure friend_count
## 1 2094382 14 19 1999 11 male 266 0
## 2 1192601 14 2 1999 11 female 6 0
## 3 2083884 14 16 1999 11 male 13 0
## 4 1203168 14 25 1999 12 female 93 0
## 5 1733186 14 4 1999 12 male 82 0
## 6 1524765 14 1 1999 12 male 15 0
## friendships_initiated likes likes_received mobile_likes
## 1 0 0 0 0
## 2 0 0 0 0
## 3 0 0 0 0
## 4 0 0 0 0
## 5 0 0 0 0
## 6 0 0 0 0
## mobile_likes_received www_likes www_likes_received
## 1 0 0 0
## 2 0 0 0
## 3 0 0 0
## 4 0 0 0
## 5 0 0 0
## 6 0 0 0
base$labels
## $x
## [1] "dob_day"
base$layers
## list()
base_histograma <- ggplot(aes(x = dob_day), data = facebook) +
geom_histogram()
base_mes_histograma <- base + geom_histogram()
base_histograma_axes <- ggplot(aes(x = dob_day), data = facebook) +
geom_histogram() +
scale_x_discrete(breaks = round(seq(1,31,4)))
aes
| x |
x |
x |
| y |
x |
x |
| colour |
x |
x |
| fill |
x |
x |
| size |
x |
x |
| shape |
|
x |
| linetype |
|
x |
| group |
|
x |
ggplot(data = facebook) + geom_histogram(aes(x = dob_day, group=as.factor(dob_month)),color="black")
ggplot(data = facebook) + geom_histogram(aes(x = dob_day, fill =as.factor(dob_month)),color="black",linetype="dashed")
ggplot(data = facebook) + geom_histogram(aes(x = dob_day, color=as.factor(dob_month)))
p <- ggplot() +
geom_histogram(data = facebook[facebook$dob_day==1 & facebook$dob_month==1 & !is.na(facebook$dob_year) ,] ,
aes(x=dob_year , fill=as.factor(age)) , color="black" , binwidth=1)
head(p$data)
## list()
p$layers
## [[1]]
## mapping: x = dob_year, fill = as.factor(age)
## geom_bar: na.rm = FALSE
## stat_bin: binwidth = 1, bins = NULL, origin = NULL, right = FALSE, na.rm = FALSE
## position_stack
head(p$layers[[1]]$data)
## userid age dob_day dob_year dob_month gender tenure friend_count
## 9 1365174 13 1 2000 1 male 81 0
## 34 1871735 14 1 1999 1 female 578 0
## 35 1459785 14 1 1999 1 male 478 0
## 36 1215208 14 1 1999 1 male 170 0
## 123 1505398 16 1 1997 1 male 108 0
## 124 2071007 16 1 1997 1 male 29 0
## friendships_initiated likes likes_received mobile_likes
## 9 0 0 0 0
## 34 0 0 0 0
## 35 0 0 0 0
## 36 0 0 0 0
## 123 0 0 0 0
## 124 0 0 0 0
## mobile_likes_received www_likes www_likes_received
## 9 0 0 0
## 34 0 0 0
## 35 0 0 0
## 36 0 0 0
## 123 0 0 0
## 124 0 0 0
p
Colors
ggplot(data=data.frame(dimensions=letters[1:2]),aes(x=dimensions,fill=dimensions))+geom_bar()+coord_polar()
ggplot(data=data.frame(dimensions=letters[1:3]),aes(x=dimensions,fill=dimensions))+geom_bar()+coord_polar()
ggplot(data=data.frame(dimensions=letters[1:5]),aes(x=dimensions,fill=dimensions))+geom_bar()+coord_polar()
ggplot(data=data.frame(dimensions=letters[1:20]),aes(x=dimensions,fill=dimensions))+geom_bar()+coord_polar()
position
fc.ten <-ggplot(aes(x = tenure/365, fill=gender), data = facebook)
fc.ten + geom_histogram(binwidth=.25,position="dodge")
fc.ten + geom_histogram(binwidth=.25,position="identity")
fc.ten + geom_histogram(binwidth=.25,position="identity",alpha=0.5)
fc.ten + geom_histogram(binwidth=.25,position="fill",alpha=0.5)
ggplot.obj <- fc.ten + geom_histogram(binwidth=.25,position="fill",alpha=0.5)
ggplot.obj$layers
## [[1]]
## geom_bar: na.rm = FALSE
## stat_bin: binwidth = 0.25, bins = NULL, origin = NULL, right = FALSE, na.rm = FALSE
## position_fill
ggplot.obj$mapping
## * x -> tenure/365
## * fill -> gender
ggplot.obj$labels
## $x
## [1] "tenure/365"
##
## $fill
## [1] "gender"
##
## $y
## [1] "count"
geom_density
fc.ten <-ggplot(aes(x = tenure/365, fill=gender), data = facebook)
fc.ten + geom_histogram(binwidth=.25,position="dodge")
fc.ten + geom_histogram(aes(y = ..count..),binwidth=.25,position="dodge")
fc.ten + geom_histogram(aes(y = ..density..),binwidth=.25,position="dodge")
fc.ten + geom_density(alpha=0.5)
fc.ten + geom_density(alpha=0.5,position="stack")
fc.ten + geom_density(alpha=0.5) + geom_histogram(aes(y = ..density..),binwidth=.25,position="dodge")
ggplot(aes(x = age), data = facebook) + geom_density(alpha=0.5)
ggplot(aes(x = age, fill=gender), data = facebook) + geom_density(alpha=0.5)
ggplot(aes(x = age, fill=gender), data = facebook[!is.na(facebook$gender),]) + geom_density(alpha=0.5)
ggplot(aes(x = age, fill=gender), data = facebook[facebook$gender=="female",])+geom_density(alpha=0.5)
Labe and Axes
ggplot(aes(x = friend_count, y = ..count..), data = subset(facebook, !is.na(gender))) +
geom_freqpoly(aes(color = gender),binwidth=25)
ggplot(aes(x = friend_count, y = ..count..), data = subset(facebook, !is.na(gender))) +
geom_freqpoly(aes(color = gender),binwidth=25) +
scale_x_continuous(limits = c(0, 1000), breaks = seq(0, 1000, 100)) +
xlab('Friend Count') +
ylab('users with that friend count')
ggplot(aes(x = friend_count, y = ..count../sum(..count..)), data = subset(facebook, !is.na(gender))) +
geom_freqpoly(aes(color = gender),binwidth=25) +
scale_x_continuous(limits = c(0, 1000), breaks = seq(0, 1000, 100)) +
scale_y_continuous(labels =c("0%","5%","10%"),breaks = c(0,0.05,0.10))+
xlab('Friend Count') +
ylab('Percentage of users with that friend count')
geom_boxplot
fcg <-ggplot(aes(x=gender,y=age), data = subset(facebook, !is.na(gender)))+
geom_boxplot()
fcg
fcg + geom_jitter(,alpha=1/20)
fcg + ylim(0,60)
fcg + scale_y_continuous(limits = c(0, 60))
fcg + coord_cartesian(ylim = c(0, 60))
Multi Layer
head(mpg)
## manufacturer model displ year cyl trans drv cty hwy fl class
## 1 audi a4 1.8 1999 4 auto(l5) f 18 29 p compact
## 2 audi a4 1.8 1999 4 manual(m5) f 21 29 p compact
## 3 audi a4 2.0 2008 4 manual(m6) f 20 31 p compact
## 4 audi a4 2.0 2008 4 auto(av) f 21 30 p compact
## 5 audi a4 2.8 1999 6 auto(l5) f 16 26 p compact
## 6 audi a4 2.8 1999 6 manual(m5) f 18 26 p compact
ggplot(data=mpg,aes(x=as.factor(cyl),y=cty))+geom_boxplot(color="blue")
ggplot(data=mpg,aes(x=as.factor(cyl),y=hwy))+geom_boxplot(color="brown")
ggplot(data=mpg,aes(x=as.factor(cyl)))+geom_boxplot(aes(y=cty),color="blue")+geom_boxplot(aes(y=hwy),color="brown")
ggplot(data=mpg,aes(x=as.factor(cyl)))+
geom_violin(aes(y=cty),color="blue",alpha=0.5)+
geom_violin(aes(y=hwy),color="brown",alpha=0.5)+
geom_point(aes(y=(cty+hwy)/2),color="black",alpha=0.5,position=position_jitter(h=0,w=0.2 ) )
geom_point
fcp <- ggplot(aes(x = age, y = friend_count), data = facebook)
fcp + geom_point()
fcp <-fcp + xlim(min(facebook$age),100)
fcp + geom_point()
fcp + geom_point ( alpha=1/20)
fcp + geom_jitter( alpha=1/20)
fcp + geom_point ( alpha=1/20) + coord_trans(y = 'sqrt')
fcp + geom_point ( alpha=1/20, position=position_jitter() ) + coord_trans(y = 'sqrt')
## Error in if (zero_range(range)) {: valor ausente donde TRUE/FALSE es necesario
fcp + geom_point ( alpha=1/20, position=position_jitter(h=0) ) + coord_trans(y = 'sqrt')
fcp + geom_point ( alpha=1/20, position=position_jitter(h=0) ) + scale_y_log10()
stat=“summary”
facebook <- as.data.table(facebook)
gruped.friend_count <- facebook[,.(friend_count_mean=mean(friend_count)),by=.(age,gender)]
gruped.friend_count
## age gender friend_count_mean
## 1: 14 male 164.1456
## 2: 14 female 362.4286
## 3: 13 male 102.1340
## 4: 13 female 259.1606
## 5: 15 male 200.6658
## ---
## 270: 33 NA 493.0000
## 271: 36 NA 515.0000
## 272: 95 NA 830.0000
## 273: 68 NA 790.0000
## 274: 50 NA 863.0000
gruped.friend_count <- spread(gruped.friend_count,gender,friend_count_mean)
gruped.friend_count
## age female male NA
## 1: 13 259.1606 102.1340 NA
## 2: 14 362.4286 164.1456 NA
## 3: 15 538.6813 200.6658 116.0000
## 4: 16 519.5145 239.6748 NA
## 5: 17 538.9943 236.4924 106.5000
## ---
## 97: 109 207.5000 163.0000 NA
## 98: 110 239.1429 410.5714 503.0000
## 99: 111 244.4286 246.5000 148.0000
## 100: 112 201.2000 594.0769 NA
## 101: 113 278.6571 410.3956 166.3333
gather(gruped.friend_count,gender,friend_count_mean,-age)
## age gender friend_count_mean
## 1 13 female 259.16062
## 2 14 female 362.42857
## 3 15 female 538.68130
## 4 16 female 519.51454
## 5 17 female 538.99434
## 6 18 female 481.97938
## 7 19 female 470.80075
## 8 20 female 380.82445
## 9 21 female 307.10637
## 10 22 female 251.91519
## 11 23 female 239.72114
## 12 24 female 237.07385
## 13 25 female 153.88349
## 14 26 female 175.13443
## 15 27 female 158.72441
## 16 28 female 154.22850
## 17 29 female 145.78139
## 18 30 female 130.57167
## 19 31 female 144.18196
## 20 32 female 125.27099
## 21 33 female 125.12393
## 22 34 female 133.09534
## 23 35 female 123.18026
## 24 36 female 121.36768
## 25 37 female 131.34301
## 26 38 female 129.90657
## 27 39 female 111.79019
## 28 40 female 113.72446
## 29 41 female 112.27832
## 30 42 female 114.06728
## 31 43 female 113.79487
## 32 44 female 126.23184
## 33 45 female 134.87387
## 34 46 female 133.71543
## 35 47 female 127.39906
## 36 48 female 116.54730
## 37 49 female 124.84435
## 38 50 female 133.03261
## 39 51 female 119.39596
## 40 52 female 130.06362
## 41 53 female 119.90717
## 42 54 female 106.35630
## 43 55 female 109.34639
## 44 56 female 116.01681
## 45 57 female 118.64242
## 46 58 female 121.38144
## 47 59 female 110.94013
## 48 60 female 124.70660
## 49 61 female 111.81140
## 50 62 female 115.11463
## 51 63 female 125.80321
## 52 64 female 103.54570
## 53 65 female 93.96193
## 54 66 female 106.15206
## 55 67 female 86.98773
## 56 68 female 326.10682
## 57 69 female 93.40078
## 58 70 female 73.97285
## 59 71 female 123.43284
## 60 72 female 84.53529
## 61 73 female 131.23392
## 62 74 female 133.48611
## 63 75 female 93.02542
## 64 76 female 70.32258
## 65 77 female 92.69000
## 66 78 female 197.39773
## 67 79 female 95.12500
## 68 80 female 195.41667
## 69 81 female 141.91525
## 70 82 female 95.44444
## 71 83 female 256.52381
## 72 84 female 363.17391
## 73 85 female 313.21951
## 74 86 female 336.71053
## 75 87 female 139.76471
## 76 88 female 246.11538
## 77 89 female 291.95652
## 78 90 female 241.00000
## 79 91 female 368.00000
## 80 92 female 708.76471
## 81 93 female 254.37500
## 82 94 female 493.15152
## 83 95 female 591.35714
## 84 96 female 544.82353
## 85 97 female 344.04762
## 86 98 female 482.35556
## 87 99 female 557.56000
## 88 100 female 338.69853
## 89 101 female 428.98413
## 90 102 female 471.61111
## 91 103 female 520.07407
## 92 104 female 443.02564
## 93 105 female 400.31034
## 94 106 female 370.20513
## 95 107 female 315.34211
## 96 108 female 371.86699
## 97 109 female 207.50000
## 98 110 female 239.14286
## 99 111 female 244.42857
## 100 112 female 201.20000
## 101 113 female 278.65714
## 102 13 male 102.13402
## 103 14 male 164.14564
## 104 15 male 200.66576
## 105 16 male 239.67478
## 106 17 male 236.49242
## 107 18 male 233.91833
## 108 19 male 254.58405
## 109 20 male 225.59212
## 110 21 male 195.32077
## 111 22 male 187.25316
## 112 23 male 184.92139
## 113 24 male 158.67225
## 114 25 male 120.07286
## 115 26 male 129.05213
## 116 27 male 121.55383
## 117 28 male 111.93434
## 118 29 male 107.44754
## 119 30 male 106.94803
## 120 31 male 103.24788
## 121 32 male 108.01306
## 122 33 male 92.04784
## 123 34 male 94.29045
## 124 35 male 83.65303
## 125 36 male 93.26812
## 126 37 male 82.09492
## 127 38 male 98.04558
## 128 39 male 93.29346
## 129 40 male 71.31250
## 130 41 male 87.22967
## 131 42 male 81.41617
## 132 43 male 91.43375
## 133 44 male 77.50096
## 134 45 male 82.94523
## 135 46 male 87.91368
## 136 47 male 88.93038
## 137 48 male 102.76275
## 138 49 male 85.27027
## 139 50 male 116.72871
## 140 51 male 83.02521
## 141 52 male 86.11043
## 142 53 male 104.12326
## 143 54 male 99.91136
## 144 55 male 116.86175
## 145 56 male 94.64232
## 146 57 male 100.64368
## 147 58 male 108.73333
## 148 59 male 92.33770
## 149 60 male 98.15015
## 150 61 male 125.98933
## 151 62 male 107.66975
## 152 63 male 128.35556
## 153 64 male 120.81928
## 154 65 male 101.97643
## 155 66 male 118.62058
## 156 67 male 90.65217
## 157 68 male 313.84055
## 158 69 male 97.50495
## 159 70 male 102.04255
## 160 71 male 105.18543
## 161 72 male 83.58871
## 162 73 male 101.77215
## 163 74 male 150.52985
## 164 75 male 115.58036
## 165 76 male 110.27381
## 166 77 male 236.74627
## 167 78 male 92.89041
## 168 79 male 80.13158
## 169 80 male 368.34375
## 170 81 male 122.69388
## 171 82 male 280.73333
## 172 83 male 255.28409
## 173 84 male 301.30769
## 174 85 male 297.51220
## 175 86 male 396.78378
## 176 87 male 473.70833
## 177 88 male 500.57143
## 178 89 male 497.31429
## 179 90 male 291.43902
## 180 91 male 350.42222
## 181 92 male 277.57576
## 182 93 male 274.80189
## 183 94 male 413.21739
## 184 95 male 300.79167
## 185 96 male 411.11429
## 186 97 male 490.02857
## 187 98 male 369.25000
## 188 99 male 343.12500
## 189 100 male 373.78689
## 190 101 male 373.67391
## 191 102 male 415.15044
## 192 103 male 427.85895
## 193 104 male 414.00000
## 194 105 male 415.44681
## 195 106 male 288.30588
## 196 107 male 393.35000
## 197 108 male 369.43898
## 198 109 male 163.00000
## 199 110 male 410.57143
## 200 111 male 246.50000
## 201 112 male 594.07692
## 202 113 male 410.39560
## 203 13 <NA> NA
## 204 14 <NA> NA
## 205 15 <NA> 116.00000
## 206 16 <NA> NA
## 207 17 <NA> 106.50000
## 208 18 <NA> NA
## 209 19 <NA> 374.00000
## 210 20 <NA> 65.00000
## 211 21 <NA> 79.00000
## 212 22 <NA> NA
## 213 23 <NA> 246.50000
## 214 24 <NA> NA
## 215 25 <NA> 25.40000
## 216 26 <NA> 65.00000
## 217 27 <NA> 7.00000
## 218 28 <NA> 27.00000
## 219 29 <NA> 41.00000
## 220 30 <NA> NA
## 221 31 <NA> 2.00000
## 222 32 <NA> NA
## 223 33 <NA> 493.00000
## 224 34 <NA> NA
## 225 35 <NA> NA
## 226 36 <NA> 515.00000
## 227 37 <NA> NA
## 228 38 <NA> 244.00000
## 229 39 <NA> NA
## 230 40 <NA> NA
## 231 41 <NA> NA
## 232 42 <NA> 19.00000
## 233 43 <NA> NA
## 234 44 <NA> NA
## 235 45 <NA> NA
## 236 46 <NA> NA
## 237 47 <NA> 37.00000
## 238 48 <NA> 43.00000
## 239 49 <NA> 73.00000
## 240 50 <NA> 863.00000
## 241 51 <NA> NA
## 242 52 <NA> 57.66667
## 243 53 <NA> 124.50000
## 244 54 <NA> 178.66667
## 245 55 <NA> 124.16667
## 246 56 <NA> 155.00000
## 247 57 <NA> 70.50000
## 248 58 <NA> 39.33333
## 249 59 <NA> 4.00000
## 250 60 <NA> 128.83333
## 251 61 <NA> 43.00000
## 252 62 <NA> 26.00000
## 253 63 <NA> 74.50000
## 254 64 <NA> 80.80000
## 255 65 <NA> 95.50000
## 256 66 <NA> 69.75000
## 257 67 <NA> 10.50000
## 258 68 <NA> 790.00000
## 259 69 <NA> 39.00000
## 260 70 <NA> 160.33333
## 261 71 <NA> NA
## 262 72 <NA> 67.50000
## 263 73 <NA> 470.00000
## 264 74 <NA> 557.66667
## 265 75 <NA> 60.33333
## 266 76 <NA> 17.00000
## 267 77 <NA> 23.50000
## 268 78 <NA> 30.00000
## 269 79 <NA> 69.00000
## 270 80 <NA> NA
## 271 81 <NA> NA
## 272 82 <NA> 98.66667
## 273 83 <NA> 21.00000
## 274 84 <NA> 254.00000
## 275 85 <NA> 9.00000
## 276 86 <NA> 64.00000
## 277 87 <NA> 52.00000
## 278 88 <NA> NA
## 279 89 <NA> 221.00000
## 280 90 <NA> 213.66667
## 281 91 <NA> 49.50000
## 282 92 <NA> 109.00000
## 283 93 <NA> 33.00000
## 284 94 <NA> 279.00000
## 285 95 <NA> 830.00000
## 286 96 <NA> 437.00000
## 287 97 <NA> NA
## 288 98 <NA> NA
## 289 99 <NA> 138.50000
## 290 100 <NA> 217.16667
## 291 101 <NA> 199.50000
## 292 102 <NA> 1346.50000
## 293 103 <NA> 280.87500
## 294 104 <NA> NA
## 295 105 <NA> 187.50000
## 296 106 <NA> 68.00000
## 297 107 <NA> NA
## 298 108 <NA> 281.76190
## 299 109 <NA> NA
## 300 110 <NA> 503.00000
## 301 111 <NA> 148.00000
## 302 112 <NA> NA
## 303 113 <NA> 166.33333
ggplot(aes(x=age,y=female/male) , data = gruped.friend_count )+
geom_line()+
geom_hline(yintercept=1 , alpha=0.3 , linetype=2)
facebook$Year_joined<-floor(2014-facebook$tenure/365)
facebook$Year_joined_buket<-cut(facebook$Year_joined, c(2004,2009,2011,2012,2014))
facebook.joined <- facebook[!is.na(gender),.(friend_count.mean=mean(friend_count),friend_count.sum=sum(friend_count)),by=.(Year_joined_buket,age)]
facebook.joined
## Year_joined_buket age friend_count.mean friend_count.sum
## 1: (2012,2014] 14 208.7742 302305
## 2: (2012,2014] 13 135.6682 57659
## 3: (2012,2014] 15 212.3026 326946
## 4: (2011,2012] 14 350.8129 157515
## 5: (2012,2014] 16 211.3181 356705
## ---
## 390: (2011,2012] 105 315.4000 1577
## 391: NA 103 137.0000 137
## 392: (2004,2009] 16 963.1429 6742
## 393: (2009,2011] 111 457.3333 1372
## 394: (2004,2009] 15 1871.0000 1871
ggplot(data=facebook.joined)+geom_point(aes(x=age,y=friend_count.sum,color=Year_joined_buket))
ggplot(data=facebook.joined)+geom_line(aes(x=age,y=friend_count.sum,color=Year_joined_buket))
fc.NoNA <- ggplot(aes(x=age,y=friend_count) , data = subset(facebook, !is.na(gender)) )
fc.NoNA + geom_point(aes(color=Year_joined_buket))
fc.NoNA + geom_point(aes(color=Year_joined_buket), stat="summary",fun.y=sum)
fc.NoNA + geom_line (aes(color=Year_joined_buket), stat="summary",fun.y=sum)
geom_line
fc.NoNA + geom_line (aes(color=Year_joined_buket), stat="summary",fun.y=mean)
fc.NoNA + geom_line (aes(color=Year_joined_buket), stat="summary",fun.y=mean)+
geom_line (stat="summary",fun.y=mean,linetype=2)
fcp + geom_point(alpha=1/10,
position=position_jitter(h=0),
color="darkgreen") +
geom_line(stat="summary",fun.y=mean) +
geom_line(stat="summary",fun.y=quantile,fun.args=list(probs=.1),linetype=2,color="blue") +
geom_line(stat="summary",fun.y=quantile,fun.args=list(probs=.5),linetype=1,color="blue") +
geom_line(stat="summary",fun.y=quantile,fun.args=list(probs=.9),linetype=2,color="blue") +
coord_trans(y = "sqrt")
ggplot( aes(x=tenure,y=friendships_initiated), data=subset(facebook,tenure>0) )+
geom_line(aes(color=Year_joined_buket), stat="summary", fun.y=mean)
line.layer <- geom_line(aes(color=Year_joined_buket), stat="summary", fun.y=mean)
ggplot( aes(x=tenure ,y=friendships_initiated/tenure), data=subset(facebook,tenure>0) ) + line.layer
ggplot( aes(x=7*round(tenure/7) ,y=friendships_initiated/tenure), data=subset(facebook,tenure>0) ) + line.layer
ggplot( aes(x=90*round(tenure/90),y=friendships_initiated/tenure), data=subset(facebook,tenure>0) ) + line.layer
geom_smooth
fsmoth <- ggplot(aes(x=tenure,y=friendships_initiated/tenure), data=subset(facebook,tenure>0) )
fsmoth + geom_smooth(aes(color=Year_joined_buket,fill=Year_joined_buket))
fsmoth + geom_smooth(aes(group=Year_joined_buket))
fsmoth + geom_smooth()
geom_rug
rug.plot <- ggplot(aes(x=tenure,y=friendships_initiated/tenure), data=subset(facebook,tenure>0) )+
geom_smooth(aes(color=Year_joined_buket,fill=Year_joined_buket))
rug.plot + geom_rug()
rug.plot + geom_rug(data=facebook[facebook$tenure>0,][sample(nrow(facebook[facebook$tenure>0,]), 1000),] ,alpha=0.1)
rug.plot + geom_rug(data=facebook[facebook$tenure>0,][sample(nrow(facebook[facebook$tenure>0,]), 1000),] ,alpha=0.1)+ coord_cartesian(ylim = c(-0.5, 5))
sample.facebook <- facebook[facebook$tenure>0,][sample(nrow(facebook[facebook$tenure>0,]), 1000),]
fc.ten.sample <-ggplot(aes(x = tenure/365, fill=gender), data = sample.facebook )
fc.ten.sample + geom_density(alpha=0.5)
fc.ten.sample + geom_density(alpha=0.5)+geom_rug(alpha=0.1)
fc.ten.sample + geom_density(alpha=0.5)+geom_rug(aes(color=gender),alpha=0.1)
Faceting
fc.ten.sample + geom_density(alpha=0.5)+geom_rug(aes(color=gender),alpha=0.1)+ facet_wrap(~gender)
f.dob_day <- ggplot(aes(x = dob_day), data = facebook) +
geom_histogram() +
scale_x_continuous(breaks = round(seq(1,31,4)))
f.dob_day + facet_wrap(~dob_month)
f.dob_day + facet_wrap(~dob_month,nrow = 2, ncol = 6)
f.dob_day + facet_grid(gender~dob_month)
f.dob_day + facet_grid(gender~dob_month,scales="free")
f.dob_day + facet_grid(gender~dob_month,scales="free",space="free")
ggpairs
library(GGally)
set.seed(1234)
facebook_subset<-facebook[,.(gender,tenure,friend_count,friendships_initiated, likes, likes_received)]
ggpairs(facebook_subset[sample.int(nrow(facebook_subset),1000),])
geom_tiles
pp <- function (n,r=4) {
x <- seq(-r*pi, r*pi, len=n)
df <- expand.grid(x=x, y=x)
df$r <- sqrt(df$x^2 + df$y^2)
df$z <- cos(df$r^2)*exp(-df$r/6)
df
}
dt <- data.table( pp(200))
dt
## x y r z
## 1: -12.56637 -12.56637 17.77153 -0.005023290
## 2: -12.44008 -12.56637 17.68245 0.004230445
## 3: -12.31378 -12.56637 17.59383 -0.005105300
## 4: -12.18749 -12.56637 17.50567 0.007714216
## 5: -12.06119 -12.56637 17.41798 -0.012093846
## ---
## 39996: 12.06119 12.56637 17.41798 -0.012093846
## 39997: 12.18749 12.56637 17.50567 0.007714216
## 39998: 12.31378 12.56637 17.59383 -0.005105300
## 39999: 12.44008 12.56637 17.68245 0.004230445
## 40000: 12.56637 12.56637 17.77153 -0.005023290
ggplot(data=dt) + geom_tile(aes(x=x, y=y, fill=z))
dt$xbind <- cut(dt$x,breaks=seq(min(dt$x),max(dt$x),length.out = 100))
dt$ybind <- cut(dt$y,breaks=seq(min(dt$y),max(dt$y),length.out = 100))
dt.bind<- dt[,.(mean.x=mean(x),mean.y=mean(y),fill.z=mean(z)),by=.(xbind,ybind)]
ggplot( data=dt[,.(fill.z=mean(z)),by=.(xbind,ybind)] ) + geom_tile(aes(x=xbind, y=ybind, fill=fill.z))
dt <- data.frame(cbind(rnorm(10000),rnorm(10000)) %*% matrix(c(2,1,3,3), nrow=2))
ggplot(data=dt) + geom_bin2d(aes(x=X1, y=X2), binwidth = c(0.2, 0.2))
ggplot(data=dt) + geom_density2d(aes(x=X1, y=X2))
ggplot(data=dt) + stat_density2d(aes(x=X1, y=X2,fill=..level..,alpha=..level..), geom="polygon")
ggplot(data=dt) + geom_bin2d(aes(x=X1, y=X2), binwidth = c(0.2, 0.2)) + geom_density2d(aes(x=X1, y=X2),color="white")
Maps
library(ggmap)
library(sp)
MunicipisCataluna <- fread("MunicipisCatalunya.csv",sep=";",stringsAsFactors=T)
MunicipisCataluna[,c("x","y"):=list(as.numeric(gsub(",",".",lon,fixed = T)),as.numeric(gsub(",",".",lat,fixed = T)))]
MunicipisCataluna[,c("lat","lon"):=NULL]
MunicipisCataluna <- unite(MunicipisCataluna,region,c(municipio,compontnt),sep=" ",remove=FALSE)
MunicipisCataluna
## region municipio codigoine compontnt order x
## 1: Guixers 1 Guixers 25111 1 1 1.520599
## 2: Guixers 1 Guixers 25111 1 2 1.529528
## 3: Guixers 1 Guixers 25111 1 3 1.531676
## 4: Guixers 1 Guixers 25111 1 4 1.538425
## 5: Guixers 1 Guixers 25111 1 5 1.545793
## ---
## 450103: Cervià de Ter 1 Cervià de Ter 17050 1 340 2.884106
## 450104: Cervià de Ter 1 Cervià de Ter 17050 1 341 2.884365
## 450105: Cervià de Ter 1 Cervià de Ter 17050 1 342 2.884485
## 450106: Cervià de Ter 1 Cervià de Ter 17050 1 343 2.884270
## 450107: Cervià de Ter 1 Cervià de Ter 17050 1 344 2.884730
## y
## 1: 42.15181
## 2: 42.15180
## 3: 42.15206
## 4: 42.15184
## 5: 42.15217
## ---
## 450103: 42.06261
## 450104: 42.06280
## 450105: 42.06305
## 450106: 42.06490
## 450107: 42.06616
ggplot(MunicipisCataluna, aes(map_id = region)) +
geom_map( aes(fill = codigoine) , color="black", map = MunicipisCataluna) +
expand_limits(x = MunicipisCataluna$x, y = MunicipisCataluna$y)+
theme( legend.position = "none" )
background.map <- get_map(location=c(mean(MunicipisCataluna$x),mean(MunicipisCataluna$y)),source="google",maptype="toner",zoom=8)
mon.shapes <- geom_polygon(data=MunicipisCataluna,aes(x = MunicipisCataluna$x, y = MunicipisCataluna$y-0.017,group = region, fill=codigoine),alpha=0.7,color=rgb(0,0,0,.3))
ggmap(background.map) +
mon.shapes +
expand_limits(x = MunicipisCataluna$x, y = MunicipisCataluna$y)+
theme(legend.position="none")
